capabilities/skills/commander/SKILL.md

---
name: Commanders
description: >-
  Use when the user asks about a commander — what one is, how to start one, why one is not firing, how much
  one costs — or when they describe work that should keep happening while they are away ("watch X and do Y",
  "every time Z, run this"). Carries what a commander is, how the pieces actually fit, and how to help
  somebody arrive at one that works. Open the Officer platform skill too if the answer needs an endpoint.
version: 1
---

# What a commander is

An agent that keeps working when nobody is watching. It waits for something, acts on it, and reports.

Mechanically it is **an ordinary chat session** that the platform has filed as a commander. Nothing else
distinguishes it: same harness, same transcript, same socket. It is a commander because of **where it runs** —
its working directory is the account's commanders directory — and `isCommandersDir` is the whole test.

That has a consequence worth stating early, because people assume otherwise: a commander is not a special
kind of agent with special powers. It is a conversation in a particular folder, plus a loop somebody started
from inside it.

# The three pieces, and which one people get wrong

**1. The conversation.** Where you and it agree what the job is. This is the part to spend time on.

**2. The wait.** A shell loop, started as a tracked background job from inside that conversation. It polls,
and when its condition is true it acts. The wait happens **in the shell** — not by the model waking up to
check. A model-side tick re-reads the whole conversation to learn nothing, and costs a turn to do it.

**3. The action.** The loop cannot do judgement — it cannot read a plan, weigh a situation, or write a report. So
when it fires it spawns a **headless agent** (`claude -p`) with a prompt telling it to read a procedure and
follow it. That agent does the work and exits.

The piece people get wrong is 3. They expect the commander itself to wake up and act. It does not: it started
a loop, and the loop starts somebody else.

# Never arm on the first turn

Not a guideline. The first exchange is for establishing what to watch and what to do about it, and a watcher
armed before that is a watcher armed on a guess — which fails silently in both directions: it never fires, or
it fires constantly, and either way it is found out days later.

There is a mechanical interlock behind the rule, and it is worth knowing so it is not mistaken for a fault.
A commander is told the paths it must record itself at, in its session preamble — and on the very first turn
those paths do not exist yet, because the transcript id is minted as that turn begins. **So if you have not
been given paths, you are on your first turn.** An agent that armed anyway would be unstoppable and
undeletable, which is the second reason for the same rule.

# When you started yourself

Officer can start you with a button instead of a prompt. When it does, everything you have been told is a
name and a working directory — the person has not said what they want yet, and they are waiting for you to
ask. That is the whole reason the button exists: writing a good opening prompt is the hard part, and asking
somebody to do it before they have talked to you gets it done badly or not at all.

**Turn one is orientation, not questions.** Read where you actually are before you ask anything. What that
means depends entirely on what the directory turns out to be — a repository, a folder somebody drops files
into, a mailbox, a library of documents, a machine that runs one script. List it, read whatever explains
it, and form a view. You are not looking for anything in particular; you are trying to stop being a
stranger before you ask somebody to explain their work to you.

**Your name is the brief.** Whoever started you chose it before anything else and it is usually the only
thing they have said — "Platform Deploys", "Invoice Inbox", "Backup Watch". Read this directory looking for
what that name refers to, and let it settle what is in scope. A name pointing at deploys means the question
you are working towards is about deploys; the fact that the repository is also mid-refactor is not your
business and asking about it wastes the turn.

**You are looking for something that HAPPENS AGAIN, not for what people here are doing.** This is the trap,
and a codebase sets it perfectly: a `TODO.md`, a list of open items and a week of commits are all right
there, and reading them produces a confident, useless question about which piece of work matters most. That
is a colleague's question. Yours is narrower — what event recurs here, and what does somebody do by hand
every time it does? Current priorities are not a trigger. Nothing you can only do once is a commander.

**Whatever that job turns out to be, look for whether it has been done here by hand already.** It usually has, and the
shape of it is on disk — a folder of previous runs, a procedure somebody wrote down, a script with the
steps already in order, a naming convention nobody documented. Finding that is worth more than any
question you could ask, because it turns "how should this work" into "is this still how you want it", and
the second question gets a much better answer.

**When they name a system, read its skill before you reason about it.** Your skills index lists what is
available here by description; the bodies load when you open one. So a system that Officer knows about —
itself included — has its knowledge somewhere better than your guess, and reaching for it is one tool call.
Do that instead of inferring how something works from its directory listing, and instead of asking them to
explain something already written down. If there is no skill for what they named, say so plainly and ask;
that is a real answer, and inventing a mechanism to fill the gap is not.

Then open with what you found, and one question. Not four — a person answers one question well and a list
badly, and the answers to questions two through four will be shaped by the answer to the first anyway.

**And keep that short.** Two or three sentences, then the question. This is the hardest rule here to
follow, because you will have just done a lot of work and it all feels worth saying — it is not. The person
is making one decision, and everything that does not help them make it is in the way of it.

So: no headings, no bullets, no inventory of what you checked, no ids, no paths, no file names unless the
question is about a file. Do not write the word "verified" — you were asked to look, and saying you looked
is not a finding. Say what you found in the way you would say it out loud to someone who just walked in:
*"Looks like you already do this by hand and there's a procedure written down — is that what you want me to
take over, or is it something else?"* That is the whole opening.

Think as hard and as long as you like. Read everything. Then say almost none of it. What you found stays
available — it is in your own history, and the next question is where the detail earns its place, once they
have told you which detail matters. A first message they have to skim is one they answer badly.

**Then work through the questions below, one at a time, in that order.** Follow the answers where they go —
this is a conversation and the interesting parts are the corrections. Do not move on from a trigger that
cannot be reduced to a shell test; that is the one question where "roughly" is not good enough.

**Before you arm anything, write the specification down and show it.** Trigger, action, baseline, what must
never happen twice, what a report contains. In their words, not a config dump. Two things come out of this:
they catch the misunderstanding while it is still cheap, and you end up with the procedure file you were
going to need anyway. Ask them to confirm it. Then, and only then, arm — and the rule below still holds,
so it is not on this turn.

# Helping somebody shape one

Most of the value is here, and it is a conversation rather than a form. Four questions, in this order:

**What is the trigger, exactly?** Not "when there is a new release" — *what file, tag, row or output changes,
and what command reveals it*. If the trigger cannot be reduced to a shell test that exits 0 or 1, there is no
commander yet, only an intention. Push until it can.

**What happens when it fires?** If the answer needs judgement, the action is a spawned agent and it needs a
written procedure to follow. Say that out loud — a procedure in a file, versioned, is what makes the same
the same job repeatable next month, and reviewable by somebody else. A prompt typed into a dialog is not.

**What must never happen twice?** This is the question nobody volunteers and it is the expensive one. A
trigger that stays true after a failed action fires again, and again. Ask what the cost of a second run is:
if it is money, or a duplicate message, or a half-applied change, the action must **claim** its work before
starting and refuse a second attempt. One attempt per unit of work, enforced by something the loop cannot
undo — a file created with `mkdir`, not a flag it sets itself.

**What does "new" mean — and this one you must supply, not ask for.** "Watch for new X" is not a condition, whatever X is —
a tag, a file in a folder, a row, an unread message, an alert. A watcher armed today sees everything that already exists, and unless something says otherwise it
will treat all of it as news and act on every item in turn. Nobody says "and ignore the ones already there",
because to a person that is obviously implied. It is not implied to a shell loop.

So a watcher needs a **baseline**, and there are only two honest kinds:

- **A record of what has been handled.** Best where acting is expensive or must not repeat: the loop skips
  anything with a record and creates one before acting. This also survives a restart, which a remembered
  baseline does not.
- **A snapshot taken at arming.** Fine where the history is genuinely irrelevant — "anything that lands from
  now on". Cheap, and it forgets everything the moment the loop is restarted, so say that out loud.

Choose one and say which, in the condition itself. A watcher with neither looks identical to a working one
until the moment it fires on a backlog.

**What does "done" look like to you?** A report is worth more than a success flag, and the parts worth
reading are the ones that are hard to reconstruct: what it skipped, what it could not verify, what it left
outstanding. Ask for those explicitly or you will get a summary of what went right.

# Writing the loop, if you are the one writing it

The background-job dialog already sends the load-bearing mechanics — use the harness's own background
mechanism, keep the wait in the shell, put the test into the shell condition, and **ask first if the
condition is not completely clear** rather than arming a guess. That last one matters more than it reads: a
wrong condition fails silently, either never firing or firing constantly, and it is found out days later.
Arming late costs a minute.

Four details the mechanics do not carry, each of which was learned by getting it wrong:

- **`OFFICER_ROOT` is empty in the sidecar's environment.** Any path built from it resolves to `/data/...`,
  so anything the loop writes to record its own progress lands where nothing
  reads it — and a watcher whose record is invisible to itself has no baseline, so it acts on the same
  work for ever. Set it explicitly in the loop.
- **Keep stderr out of a `--output-format=stream-json` pipe.** The CLI prints warnings there — a
  connectors notice, among others — and one of them landing in the stream corrupts the first `jq` parse.
  Redirect it to its own reader.
- **`jq --unbuffered`**, or the job panel shows nothing for as long as the work takes and reads as hung.
  A background job that produces no output is indistinguishable from a dead one.
- **The claim goes before the spawn, not inside the action.** If the action claims its own work, an action
  that dies before claiming has claimed nothing and will run again.

# Things that are true and surprising

- **Its cost line understates.** The recorded cost counts the commander's OWN turns — one row per `result`
  that passes through the platform's chat socket. A spawned agent's cost never touches that socket, so a
  commander that spent several dollars through its children can honestly display cents. Do not quote the
  number as total spend.
- **A spawned agent cannot be found from its parent.** Nothing links them: the child's transcript looks
  exactly like any other session, and entry types that appear to mark one (`queue-operation`, `ai-title`,
  `last-prompt`) are the harness's own and appear in both. If a link is wanted, the loop must **print or
  record the child's session id itself** — there is no way to recover it afterwards.
- **A child transcript is not permanent.** It is readable while it lives and for a while after. Two from a
  previous day were gone. Anything worth keeping must be captured while it runs.
- **Reach what you are watching by the shortest path available.** A public hostname for something sitting on
  the same machine goes out and back through whatever fronts it, and shared-IP rate limiting there refuses
  connections for long stretches — presenting as an access-rights error, which it is not. Minutes of
  detection latency become hours. The Officer-specific instance of this is in the **Deploying Officer** skill.
- **The platform may not know a watcher exists.** Its bookkeeping engages only for the fire behaviour that
  hands back and re-arms. Started another way, the loop runs perfectly and the row still reads unarmed, so
  the UI shows no watcher and has nothing to disarm.

# When something is not firing

In this order, because each rules out the one below:

1. **Is the loop alive?** It is a tracked background job — look at the job, not at the agent.
2. **Is its condition ever true?** Run the test by hand, in the same shell form the loop uses.
3. **Can it reach what it polls?** An access-rights error on a repository or an endpoint that plainly exists
   is usually a rate-limited public path, not a credential.
4. **Has it already claimed this work?** A refusal to act twice looks identical to a failure to notice.
5. **Only then** the model, the prompt or the procedure.

# Where to look next

For endpoints, permissions or why something is refused, open the **Officer platform** skill. For a deploy —
the worked example of everything above, with a real procedure and a real fleet behind it — open the
**Deploying Officer** skill.